Baichuan-Omni Technical Report
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916543091179520 |
|---|---|
| author | Li, Yadong Sun, Haoze Lin, Mingan Li, Tianpeng Dong, Guosheng Zhang, Tao Ding, Bowen Song, Wei Cheng, Zhenglin Huo, Yuqi Chen, Song Li, Xu Pan, Da Zhang, Shusen Wu, Xin Liang, Zheng Liu, Jun Zhang, Tao Lu, Keer Zhao, Yaqi Shen, Yanjun Yang, Fan Yu, Kaicheng Lin, Tao Xu, Jianhua Zhou, Zenan Chen, Weipeng |
| author_facet | Li, Yadong Sun, Haoze Lin, Mingan Li, Tianpeng Dong, Guosheng Zhang, Tao Ding, Bowen Song, Wei Cheng, Zhenglin Huo, Yuqi Chen, Song Li, Xu Pan, Da Zhang, Shusen Wu, Xin Liang, Zheng Liu, Jun Zhang, Tao Lu, Keer Zhao, Yaqi Shen, Yanjun Yang, Fan Yu, Kaicheng Lin, Tao Xu, Jianhua Zhou, Zenan Chen, Weipeng |
| contents | The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08565 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Baichuan-Omni Technical Report Li, Yadong Sun, Haoze Lin, Mingan Li, Tianpeng Dong, Guosheng Zhang, Tao Ding, Bowen Song, Wei Cheng, Zhenglin Huo, Yuqi Chen, Song Li, Xu Pan, Da Zhang, Shusen Wu, Xin Liang, Zheng Liu, Jun Zhang, Tao Lu, Keer Zhao, Yaqi Shen, Yanjun Yang, Fan Yu, Kaicheng Lin, Tao Xu, Jianhua Zhou, Zenan Chen, Weipeng Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction. |
| title | Baichuan-Omni Technical Report |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.08565 |